Javascript regular expression to validate URL

Question

I am validating URL with following regular expression. I want to validate google.com also but it returns false. What can be changed in R.E below to validate google.com.

console.log(learnRegExp('http://www.google-com.123')); // false
console.log(learnRegExp('https://www.google-com.com')); // true
console.log(learnRegExp('http://google-com.com')); // true
console.log(learnRegExp('http://google.com')); //true
console.log(learnRegExp('google.com')); //false

function learnRegExp(){
  return /^(ftp|https?):\/\/+(www\.)?[a-z0-9\-\.]{3,}\.[a-z]{3}$/.test(learnRegExp.arguments[0]);
}

Answer 1

Why not have multiple regex for each case?

1. Valid alphanumeric url: /^https?:\/\/([\w\d\-]+\.)+\w{2,}(\/.+)?$/

   Works with http://sub_do-main.a.co to things like https://a.a.a.a.aa/my-awesome_url?asd=12. You can try it at: https://regex101.com/r/oXFuGy/2

2. IPv4, short and fast but not 100% accurate (it is used by validator.js): /^(\d{1,3}(\.|$)){4}/. It allows things like 999.999.999.999.

3. IPv4, larger, slower but 100% accurate: ^(((25[0-5])|(2[0-4]\d)|(1\d{2})|(\d{1,2}))\.){3}(((25[0-5])|(2[0-4]\d)|(1\d{2})|(\d{1,2})))$. Found it here: https://stackoverflow.com/a/50650510/2862917.
4. IPv6 (I don't know exactly if this is the best/accurate/faster approach: ^(([\da-fA-F]{0,4}:){1,7}[\da-fA-F]{0,4})$. Found it here: Regular expression that matches valid IPv6 addresses which has as a first answer why would be better to stop using regex to try to validate IP's (at least those v6).

Answer 2

This validate the URL in general

console.log('http://www.google-com.123.com', validateUrl('http://www.google-com.123.com')); // true 
console.log('http://www.google-com.123', validateUrl('http://www.google-com.123')); // false 
console.log('https://www.google-com.com', validateUrl('https://www.google-com.com')); // true 
console.log('http://google-com.com', validateUrl('http://google-com.com')); // true 
console.log('http://google.com', validateUrl('http://google.com')); //true 
console.log('google.com', validateUrl('google.com')); //false
console.log('http://www.gfh.', validateUrl('http://www.gfh.')); //false
console.log('http://www.gfh.c', validateUrl('http://www.gfh.c')); //false
console.log('http://www.gfh:800000', validateUrl('http://www.gfh:800000')); //false
console.log('www.google.com ', validateUrl('www.google.com ')); //false
console.log('http://google', validateUrl('http://google')); //false
console.log('//cdnblabla.cloudfront.net/css/app.css', validateUrl('//cdnblabla.cloudfront.net/css/app.css')); //true

function validateUrl(value) {
  return /^(?:(?:(?:https?|ftp):)?\/\/)(?:\S+(?::\S*)?@)?(?:(?!(?:10|127)(?:\.\d{1,3}){3})(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z\u00a1-\uffff0-9]-*)*[a-z\u00a1-\uffff0-9]+)(?:\.(?:[a-z\u00a1-\uffff0-9]-*)*[a-z\u00a1-\uffff0-9]+)*(?:\.(?:[a-z\u00a1-\uffff]{2,})))(?::\d{2,5})?(?:[/?#]\S*)?$/i.test(value);
}

Should Match

["//www.google.com", "//cdnblabla.cloudfront.net/css/app.css", "http://✪df.ws/123", "http://userid:password@example.com:8080", "http://userid:password@example.com:8080/", "http://userid@example.com", "http://userid@example.com/", "http://userid@example.com:8080", "http://userid@example.com:8080/", "http://userid:password@example.com", "http://userid:password@example.com/", "http://142.42.1.1/", "http://142.42.1.1:8080/", "http://➡.ws/䨹", "http://⌘.ws", "http://⌘.ws/", "http://foo.com/blah_(wikipedia)#cite-1", "http://foo.com/blah_(wikipedia)_blah#cite-1", "http://foo.com/unicode_(✪)_in_parens", "http://foo.com/(something)?after=parens", "http://☺.damowmow.com/", "http://code.google.com/events/#&product=browser", "http://j.mp", "ftp://foo.bar/baz", "http://foo.bar/?q=Test%20URL-encoded%20stuff", "http://مثال.إختبار", "http://例子.测试"].map(function(url) {
  console.log(url, validateUrl(url));
});

function validateUrl(value) {
  return /^(?:(?:(?:https?|ftp):)?\/\/)(?:\S+(?::\S*)?@)?(?:(?!(?:10|127)(?:\.\d{1,3}){3})(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z\u00a1-\uffff0-9]-*)*[a-z\u00a1-\uffff0-9]+)(?:\.(?:[a-z\u00a1-\uffff0-9]-*)*[a-z\u00a1-\uffff0-9]+)*(?:\.(?:[a-z\u00a1-\uffff]{2,})))(?::\d{2,5})?(?:[/?#]\S*)?$/i.test(value);
}

Should Fail

["http://", "http://.", "http://..", "http://../", "http://?", "http://??", "http://??/", "http://#", "http://##", "http://##/", "http://foo.bar?q=Spaces should be encoded", "//", "//a", "///a", "///", "http:///a", "foo.com", "rdar://1234", "h://test", "http:// shouldfail.com", ":// should fail", "http://foo.bar/foo(bar)baz quux", "ftps://foo.bar/", "http://-error-.invalid/", "http://-a.b.co", "http://a.b-.co", "http://0.0.0.0", "http://10.1.1.0", "http://10.1.1.255", "http://224.1.1.1", "http://1.1.1.1.1", "http://123.123.123", "http://3628126748", "http://.www.foo.bar/", "http://www.foo.bar./", "http://.www.foo.bar./", "http://10.1.1.1", "http://10.1.1.254"].map(function(url) {
  console.log(url, validateUrl(url));
});

function validateUrl(value) {
  return /^(?:(?:(?:https?|ftp):)?\/\/)(?:\S+(?::\S*)?@)?(?:(?!(?:10|127)(?:\.\d{1,3}){3})(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z\u00a1-\uffff0-9]-*)*[a-z\u00a1-\uffff0-9]+)(?:\.(?:[a-z\u00a1-\uffff0-9]-*)*[a-z\u00a1-\uffff0-9]+)*(?:\.(?:[a-z\u00a1-\uffff]{2,})))(?::\d{2,5})?(?:[/?#]\S*)?$/i.test(value);
}

How it works

// protocol identifier
"(?:(?:(?:https?|ftp):)?//)"
// user:pass authentication
"(?:\\S+(?::\\S*)?@)?"
"(?:"
// IP address exclusion
// private & local networks
"(?!(?:10|127)(?:\\.\\d{1,3}){3})"
"(?!(?:169\\.254|192\\.168)(?:\\.\\d{1,3}){2})"
"(?!172\\.(?:1[6-9]|2\\d|3[0-1])(?:\\.\\d{1,3}){2})"
// IP address dotted notation octets
// excludes loopback network 0.0.0.0
// excludes reserved space >= 224.0.0.0
// excludes network & broacast addresses
// (first & last IP address of each class)
"(?:[1-9]\\d?|1\\d\\d|2[01]\\d|22[0-3])"
"(?:\\.(?:1?\\d{1,2}|2[0-4]\\d|25[0-5])){2}"
"(?:\\.(?:[1-9]\\d?|1\\d\\d|2[0-4]\\d|25[0-4]))"
"|"
// host name
"(?:(?:[a-z\\u00a1-\\uffff0-9]-*)*[a-z\\u00a1-\\uffff0-9]+)"
// domain name
"(?:\\.(?:[a-z\\u00a1-\\uffff0-9]-*)*[a-z\\u00a1-\\uffff0-9]+)*"
// TLD identifier
"(?:\\.(?:[a-z\\u00a1-\\uffff]{2,})))"
// port number
"(?::\\d{2,5})?"
// resource path
"(?:[/?#]\\S*)?"

All this comes from this gist, i hope that this fill all your needs

Answer 3

This is perfect for me. I hope it will be perfect for someone else! :)

/^((https?):\/\/)?([w|W]{3}\.)+[a-zA-Z0-9\-\.]{3,}\.[a-zA-Z]{2,}(\.[a-zA-Z]{2,})?$/

Answer 4

^... symbol is saying begins with so the final log makes sense, i.e. the string does not begin with ftp or http(s). Youre also saying with ...$ that the end that the string must finish with three letters which again where it fails (line 2) it does not end like this. Some minor adjustments and you should be there.

Answer 5

Here you go, you need to make "ftp/http(s)://" not a MUST. Use "?" for this.

function learnRegExp(){
  return /((ftp|https?):\/\/)?(www\.)?[a-z0-9\-\.]{3,}\.[a-z]{3}$/.test(learnRegExp.arguments[0]);
}

Answer 6

/(http|https):\/\/(\w+:{0,1}\w*@)?(\S+)(:[0-9]+)?(\/|\/([\w#!:.?+=&%@!\-\/]))?/